Action Sequence Augmentation for Early Graph-based Anomaly Detection
This addresses the need for early detection of online abuse to minimize financial loss, though it is an incremental improvement over existing graph-based anomaly detection techniques.
The paper tackles the problem of early anomaly detection in user behavior on web platforms, where existing graph-based methods perform poorly with limited data. The proposed Eland framework improves anomaly detection performance at an earlier stage by up to 15% on AUC compared to non-augmented methods that require more observed data.
The proliferation of web platforms has created incentives for online abuse. Many graph-based anomaly detection techniques are proposed to identify the suspicious accounts and behaviors. However, most of them detect the anomalies once the users have performed many such behaviors. Their performance is substantially hindered when the users' observed data is limited at an early stage, which needs to be improved to minimize financial loss. In this work, we propose Eland, a novel framework that uses action sequence augmentation for early anomaly detection. Eland utilizes a sequence predictor to predict next actions of every user and exploits the mutual enhancement between action sequence augmentation and user-action graph anomaly detection. Experiments on three real-world datasets show that Eland improves the performance of a variety of graph-based anomaly detection methods. With Eland, anomaly detection performance at an earlier stage is better than non-augmented methods that need significantly more observed data by up to 15% on the Area under the ROC curve.